/[suikacvs]/markup/html/whatpm/t/HTML-tokenizer.t
Suika

Diff of /markup/html/whatpm/t/HTML-tokenizer.t

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.23 by wakaba, Sun Mar 2 14:41:28 2008 UTC revision 1.29 by wakaba, Mon Mar 3 13:15:54 2008 UTC
# Line 1  Line 1 
1  #!/usr/bin/perl  #!/usr/bin/perl
2  use strict;  use strict;
3    
4    my $DEBUG = $ENV{DEBUG};
5    
6  my $dir_name;  my $dir_name;
7  my $test_dir_name;  my $test_dir_name;
8  BEGIN {  BEGIN {
# Line 24  BEGIN { Line 26  BEGIN {
26  }  }
27    
28  use Test;  use Test;
29  BEGIN { plan tests => 416 }  BEGIN { plan tests => 471 }
30    
31  use Data::Dumper;  use Data::Dumper;
32  $Data::Dumper::Useqq = 1;  $Data::Dumper::Useqq = 1;
# Line 34  sub Data::Dumper::qquote { Line 36  sub Data::Dumper::qquote {
36    return q<qq'> . $s . q<'>;    return q<qq'> . $s . q<'>;
37  } # Data::Dumper::qquote  } # Data::Dumper::qquote
38    
39    if ($DEBUG) {
40      my $not_found = {%$Whatpm::HTML::Debug::cp};
41    
42      $Whatpm::HTML::Debug::cp_pass = sub {
43        my $id = shift;
44        delete $not_found->{$id};
45      };
46    
47      END {
48        for my $id (sort {$a <=> $b || $a cmp $b} grep {!/^[ti]/}
49                    keys %$not_found) {
50          print "# checkpoint $id is not reached\n";
51        }
52      }
53    }
54    
55  use Whatpm::HTML;  use Whatpm::HTML;
56    
57  for my $file_name (grep {$_} split /\s+/, qq[  for my $file_name (grep {$_} split /\s+/, qq[
# Line 85  for my $file_name (grep {$_} split /\s+/ Line 103  for my $file_name (grep {$_} split /\s+/
103        my $p = Whatpm::HTML->new;        my $p = Whatpm::HTML->new;
104        my $i = 0;        my $i = 0;
105        my @token;        my @token;
106        $p->{set_next_input_character} = sub {        $p->{set_next_char} = sub {
107          my $self = shift;          my $self = shift;
108    
109          pop @{$self->{prev_input_character}};          pop @{$self->{prev_char}};
110          unshift @{$self->{prev_input_character}}, $self->{next_input_character};          unshift @{$self->{prev_char}}, $self->{next_char};
111    
112          $self->{next_input_character} = -1 and return if $i >= length $s;          $self->{next_char} = -1 and return if $i >= length $s;
113          $self->{next_input_character} = ord substr $s, $i++, 1;          $self->{next_char} = ord substr $s, $i++, 1;
114    
115          if ($self->{next_input_character} == 0x000D) { # CR          if ($self->{next_char} == 0x000D) { # CR
116            $i++ if substr ($s, $i, 1) eq "\x0A";            $i++ if substr ($s, $i, 1) eq "\x0A";
117            $self->{next_input_character} = 0x000A; # LF # MUST            $self->{next_char} = 0x000A; # LF # MUST
118          } elsif ($self->{next_input_character} > 0x10FFFF) {          } elsif ($self->{next_char} > 0x10FFFF) {
119            $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
120            push @token, 'ParseError';            push @token, 'ParseError';
121          } elsif ($self->{next_input_character} == 0x0000) { # NULL          } elsif ($self->{next_char} == 0x0000) { # NULL
122            $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
123            push @token, 'ParseError';            push @token, 'ParseError';
124          }          }
125        };        };
126        $p->{prev_input_character} = [-1, -1, -1];        $p->{prev_char} = [-1, -1, -1];
127        $p->{next_input_character} = -1;        $p->{next_char} = -1;
128                
129        $p->{parse_error} = sub {        $p->{parse_error} = sub {
130          push @token, 'ParseError';          push @token, 'ParseError';
# Line 142  for my $file_name (grep {$_} split /\s+/ Line 160  for my $file_name (grep {$_} split /\s+/
160            $test_token->[1] = $token->{name};            $test_token->[1] = $token->{name};
161            $test_token->[2] = $token->{public_identifier};            $test_token->[2] = $token->{public_identifier};
162            $test_token->[3] = $token->{system_identifier};            $test_token->[3] = $token->{system_identifier};
163            $test_token->[4] = $token->{correct} ? 1 : 0;            $test_token->[4] = $token->{quirks} ? 0 : 1;
164          }          }
165    
166          if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and          if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and
Legend:
Removed from v.1.23  
changed lines
  Added in v.1.29
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24